General model by thkim0305 · 3.53B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
llama3.2_3B_vl fits comfortably in your 24 GB Mac using Q8_0 quantization, using 18% of your RAM.
~46 tok/s
Q8_0 · 4.4 GB · Estimated
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 Recommended | 4.4 GB | ~46 tok/s | ✓ |
| Q6_K | 3.6 GB | ~60 tok/s | ✓ |
| Q5_K_M | 3.1 GB | ~70 tok/s | ✓ |
| Q4_K_M | 2.8 GB | ~82 tok/s | ✓ |
| Q3_K_M | 2.4 GB | ~100 tok/s | ✓ |
| Q2_K | 2.0 GB | ~129 tok/s | ✓ |
GGUF Sources
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free